Embedded Files
工作坊 (三)
工作坊 (三)
【講題】
縱向成長模式分析
Longitudinal Growth Curve Models
【講者】
劉長萱 博士 Dr. Michelle Liou
中央研究院統計科學研究所 研究員
Research Fellow - Institute of Statistical Science at Academia Sinica
【語言】中文
【日期】2019 / 12 / 12 (四)
【時間】
12:00 ~ 13:00 課前交流與討論
13:00 ~ 14:30 課程（一）
14:30 ~ 15:00 茶敘
15:00 ~ 16:30 課程（二）
16:40 ~ 18:10 課後交流與討論
【地點】國立政治大學 藝文中心二樓 舜文大講堂
講題內容與重要性
講題內容與重要性
It has been a common practice in behavioral research to collect observations across either discrete or continuous time points within each individual subject (i.e., healthy volunteers, patients, or animals). For data analysis, it would be important to model the changes over time points for each subject and for a comparison between several groups of subjects. This 3-hour seminar introduces the statistical methods for analyzing repeated measures or longitudinal data. Because there are many statistical methods available for modeling changes, the seminar gives a focus on these methods commonly cited in the behavioral science journals, including MANOVA, repeated measures ANOVA, split-plot ANOVA, univariate mixed effect models, and multivariate mixed effect models. The seminar will also provide a brief overview on other methods useful for longitudinal data analyses such as discretetime hazard model, and cox regression models.
課程大綱
課程大綱
Classical methods for analyzing repeated measures data: A comparison between MANOVA, repeated measures ANOVA, split plot ANOVA.
Univariate and multivariate mixed effect models for growth curve analysis.
Step-by-step SPSS procedures for analyzing longitudinal data, and interpretation of SPSS outputs.
Discrete-time hazard model and cox regression models.
建議閱讀文獻
建議閱讀文獻
Singer, J. D. & Willett, J. B. (2003). Applied Longitudinal Data Analysis: Modeling Change and Event Occurrence. New York: Oxford University Press.
Heck, R. H.; Thomas, S. L. & Tabata, L. N. (2010). Multilevel and Longitudinal Modeling with IBM SPSS. New York: Taylor and Francis Group.
20191212縱向成長模式分析.pdfReport abuse